[Qemu-ppc] [PATCH V2 09/19] Add VSX ISA2.06 xsqrt Instructions

[Tom Musta]

This patch adds the VSX floating point square root instructions
defined by V2.06 of the PowerPC ISA: xssqrtdp, xvsqrtdp, xvsqrtsp.

V2: re-implemented the VSX_SQRT macro.

Signed-off-by: Tom Musta <address@hidden>
---
 target-ppc/fpu_helper.c |   44 ++++++++++++++++++++++++++++++++++++++++++++
 target-ppc/helper.h     |    3 +++
 target-ppc/translate.c  |    6 ++++++
 3 files changed, 53 insertions(+), 0 deletions(-)

diff --git a/target-ppc/fpu_helper.c b/target-ppc/fpu_helper.c
index 5908e41..060e6a0 100644
--- a/target-ppc/fpu_helper.c
+++ b/target-ppc/fpu_helper.c
@@ -1939,3 +1939,47 @@ void helper_##op(CPUPPCState *env, uint32_t opcode)      
                     \
 VSX_RE(xsredp, 1, float64, f64, 1)
 VSX_RE(xvredp, 2, float64, f64, 0)
 VSX_RE(xvresp, 4, float32, f32, 0)
+
+/* VSX_SQRT - VSX floating point square root
+ *   op    - instruction mnemonic
+ *   nels  - number of elements (1, 2 or 4)
+ *   tp    - type (float32 or float64)
+ *   fld   - vsr_t field (f32 or f64)
+ *   sfprf - set FPRF
+ */
+#define VSX_SQRT(op, nels, tp, fld, sfprf)                                   \
+void helper_##op(CPUPPCState *env, uint32_t opcode)                          \
+{                                                                            \
+    ppc_vsr_t xt, xb;                                                        \
+    int i;                                                                   \
+                                                                             \
+    getVSR(xB(opcode), &xb, env);                                            \
+    getVSR(xT(opcode), &xt, env);                                            \
+    helper_reset_fpstatus(env);                                              \
+                                                                             \
+    for (i = 0; i < nels; i++) {                                             \
+        float_status tstat = env->fp_status;                                 \
+        set_float_exception_flags(0, &tstat);                                \
+        xt.fld[i] = tp##_sqrt(xb.fld[i], &tstat);                            \
+        env->fp_status.float_exception_flags |= tstat.float_exception_flags; \
+                                                                             \
+        if (unlikely(tstat.float_exception_flags & float_flag_invalid)) {    \
+            if (tp##_is_neg(xb.fld[i]) && !tp##_is_zero(xb.fld[i])) {        \
+                fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSQRT, sfprf);   \
+            } else if (tp##_is_signaling_nan(xb.fld[i])) {                   \
+                fload_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN, sfprf);   \
+            }                                                                \
+        }                                                                    \
+                                                                             \
+        if (sfprf) {                                                         \
+            helper_compute_fprf(env, xt.fld[i], sfprf);                      \
+        }                                                                    \
+    }                                                                        \
+                                                                             \
+    putVSR(xT(opcode), &xt, env);                                            \
+    helper_float_check_status(env);                                          \
+}
+
+VSX_SQRT(xssqrtdp, 1, float64, f64, 1)
+VSX_SQRT(xvsqrtdp, 2, float64, f64, 0)
+VSX_SQRT(xvsqrtsp, 4, float32, f32, 0)
diff --git a/target-ppc/helper.h b/target-ppc/helper.h
index fe5b61c..a6e7e62 100644
--- a/target-ppc/helper.h
+++ b/target-ppc/helper.h
@@ -256,18 +256,21 @@ DEF_HELPER_2(xssubdp, void, env, i32)
 DEF_HELPER_2(xsmuldp, void, env, i32)
 DEF_HELPER_2(xsdivdp, void, env, i32)
 DEF_HELPER_2(xsredp, void, env, i32)
+DEF_HELPER_2(xssqrtdp, void, env, i32)

 DEF_HELPER_2(xvadddp, void, env, i32)
 DEF_HELPER_2(xvsubdp, void, env, i32)
 DEF_HELPER_2(xvmuldp, void, env, i32)
 DEF_HELPER_2(xvdivdp, void, env, i32)
 DEF_HELPER_2(xvredp, void, env, i32)
+DEF_HELPER_2(xvsqrtdp, void, env, i32)

 DEF_HELPER_2(xvaddsp, void, env, i32)
 DEF_HELPER_2(xvsubsp, void, env, i32)
 DEF_HELPER_2(xvmulsp, void, env, i32)
 DEF_HELPER_2(xvdivsp, void, env, i32)
 DEF_HELPER_2(xvresp, void, env, i32)
+DEF_HELPER_2(xvsqrtsp, void, env, i32)

 DEF_HELPER_2(efscfsi, i32, env, i32)
 DEF_HELPER_2(efscfui, i32, env, i32)
diff --git a/target-ppc/translate.c b/target-ppc/translate.c
index d2060b7..c5c97ba 100644
--- a/target-ppc/translate.c
+++ b/target-ppc/translate.c
@@ -7300,18 +7300,21 @@ GEN_VSX_HELPER_2(xssubdp, 0x00, 0x05, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xsmuldp, 0x00, 0x06, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xsdivdp, 0x00, 0x07, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xsredp, 0x14, 0x05, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xssqrtdp, 0x16, 0x04, 0, PPC2_VSX)

 GEN_VSX_HELPER_2(xvadddp, 0x00, 0x0C, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvsubdp, 0x00, 0x0D, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvmuldp, 0x00, 0x0E, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvdivdp, 0x00, 0x0F, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvredp, 0x14, 0x0D, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvsqrtdp, 0x16, 0x0C, 0, PPC2_VSX)

 GEN_VSX_HELPER_2(xvaddsp, 0x00, 0x08, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvsubsp, 0x00, 0x09, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvmulsp, 0x00, 0x0A, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvdivsp, 0x00, 0x0B, 0, PPC2_VSX)
 GEN_VSX_HELPER_2(xvresp, 0x14, 0x09, 0, PPC2_VSX)
+GEN_VSX_HELPER_2(xvsqrtsp, 0x16, 0x08, 0, PPC2_VSX)

 #define VSX_LOGICAL(name, tcg_op)                                    \
 static void glue(gen_, name)(DisasContext * ctx)                     \
@@ -10000,18 +10003,21 @@ GEN_XX3FORM(xssubdp, 0x00, 0x05, PPC2_VSX),
 GEN_XX3FORM(xsmuldp, 0x00, 0x06, PPC2_VSX),
 GEN_XX3FORM(xsdivdp, 0x00, 0x07, PPC2_VSX),
 GEN_XX2FORM(xsredp,  0x14, 0x05, PPC2_VSX),
+GEN_XX2FORM(xssqrtdp,  0x16, 0x04, PPC2_VSX),

 GEN_XX3FORM(xvadddp, 0x00, 0x0C, PPC2_VSX),
 GEN_XX3FORM(xvsubdp, 0x00, 0x0D, PPC2_VSX),
 GEN_XX3FORM(xvmuldp, 0x00, 0x0E, PPC2_VSX),
 GEN_XX3FORM(xvdivdp, 0x00, 0x0F, PPC2_VSX),
 GEN_XX2FORM(xvredp,  0x14, 0x0D, PPC2_VSX),
+GEN_XX2FORM(xvsqrtdp,  0x16, 0x0C, PPC2_VSX),

 GEN_XX3FORM(xvaddsp, 0x00, 0x08, PPC2_VSX),
 GEN_XX3FORM(xvsubsp, 0x00, 0x09, PPC2_VSX),
 GEN_XX3FORM(xvmulsp, 0x00, 0x0A, PPC2_VSX),
 GEN_XX3FORM(xvdivsp, 0x00, 0x0B, PPC2_VSX),
 GEN_XX2FORM(xvresp, 0x14, 0x09, PPC2_VSX),
+GEN_XX2FORM(xvsqrtsp, 0x16, 0x08, PPC2_VSX),

 #undef VSX_LOGICAL
 #define VSX_LOGICAL(name, opc2, opc3, fl2) \
--
1.7.1